AI Vulnerability Expert - Fully Remote | Upto $90/hr

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .

Position: LLM Red Team Specialist — Failure Modes & Edge Cases
Type: Contract
Compensation: $60–$90/hour
Location: Remote
Commitment: 35 hours/week
Role Responsibilities

- Evaluate frontier AI models on coding, ML , and analysis tasks to identify vulnerabilities and failure modes.

- Design complex tasks that challenge models and are fair for grading.

- Document findings with clear evidence and reproducible steps.

- Collaborate with task authors to close loopholes and improve grading.

- Share insights with researchers to enhance benchmark quality.

- Work independently and asynchronously to meet deadlines and improve AI model performance .

Qualifications

Must-Have

- MSc or PhD in a STEM field or equivalent experience.

- 1+ years in research, research-engineering, security, or AI evaluation.

- Experience identifying vulnerabilities in LLMs or ML systems .

- Proficiency in Python and Git .

- Familiarity with LLM capabilities and evaluation techniques.

- Ability to work 35 hours/week .

Preferred
- Experience in AI training , model evaluation, or benchmark/task authoring.

Resources & Support

- For details about the interview process and platform information, please check:

- For any help or support, reach out to:

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.

Originally posted on Himalayas